MovingCables software
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F24%3A00386016" target="_blank" >RIV/68407700:21730/24:00386016 - isvavai.cz</a>
Result on the web
<a href="https://github.com/holesond/movingcables" target="_blank" >https://github.com/holesond/movingcables</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
MovingCables software
Original language description
MovingCables software contains MfnProb (FT) for estimating optical flow in scenes with moving cables and for densely segmenting moving cables in color images. It also contains custom image compositor software tools for creating new datasets derived from the MovingCables dataset.
Czech name
—
Czech description
—
Classification
Type
R - Software
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotics and advanced industrial production</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Internal product ID
MovingCables software
Technical parameters
Manipulating cluttered cables, hoses or ropes is challenging for both robots and humans. Humans often simplify these perceptually challenging tasks by pulling or pushing tangled cables and observing the resulting motions. We would like to build a similar system -- in accordance with the interactive perception paradigm -- to aid robotic cable manipulation. Implemented within MovingCables software, the MfnProb FT cable motion segmentation method that densely labels moving cable image pixels is a key building block of such a system. The MfnProb FT method reaches the highest recorded mean Intersection over Union (IoU) moving cable segmentation score of 0.7673 and the lowest mean endpoint error (EPE) of estimated optical flow of 0.32 pixels on the test set of the MovingCables dataset.
Economical parameters
MovingCables software might become a key component of a robotic system able to autonomously assemble or install wiring harnesses in industrial settings. Such a system might reduce manufacturing costs by replacing human workers, enable wiring harness assembly in countries with high labour costs, or increase manufacturing process speed, precision and reliability. Autonomously maintaining data centers might be another possible application area in the future.
Owner IČO
68407700
Owner name
České vysoké učení technické v Praze